diff --git a/Machine_Learning_Final_Project_Image_Analysis.ipynb b/Machine_Learning_Final_Project_Image_Analysis.ipynb
index 704066b..07c8a1d 100644
--- a/Machine_Learning_Final_Project_Image_Analysis.ipynb
+++ b/Machine_Learning_Final_Project_Image_Analysis.ipynb
@@ -32,10 +32,12 @@
           "base_uri": "https://localhost:8080/",
           "height": 672
         },
-        "outputId": "2fee98d0-9d00-4ead-b762-44e35b2c7a46"
+        "outputId": "b12075c9-adb7-4e0e-d28f-e443b6683b9f"
       },
       "source": [
+        "\"\"\"Utilize histogram matching to normalize images? https://scikit-image.org/docs/stable/auto_examples/transform/plot_histogram_matching.html#sphx-glr-auto-examples-transform-plot-histogram-matching-py\"\"\"\n",
         "## For Image portion\n",
+        "\n",
         "from google.colab import drive\n",
         "drive.mount('/content/gdrive')\n",
         "from PIL import Image\n",
@@ -58,9 +60,8 @@
         "\n",
         "filename='HP-16_0.tif'\n",
         "im=io.imread(filename)\n",
-        "cropim=im[0:4095,0:6143]#.crop(0,0,6143,4095)\n",
-        "#im = array(Image.open(filename))\n",
-        "#plt.imshow(im, cmap=plt.cm.gray)\n",
+        "cropim=im[0:4095,0:6143] #for croping out scalebar\n",
+        "\n",
         "plt.imshow(cropim, cmap=plt.cm.gray)\n",
         "\n",
         "#noisy_image = img_as_ubyte(data.camera())\n",
@@ -76,14 +77,14 @@
         "\n",
         "plt.tight_layout()\n"
       ],
-      "execution_count": 22,
+      "execution_count": 4,
       "outputs": [
         {
           "output_type": "stream",
           "text": [
-            "Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n",
+            "Mounted at /content/gdrive\n",
             "posix\n",
-            "/content/gdrive/My Drive/PhD Image Processing/Processed Images/UAB/HP-16\n"
+            "/content\n"
           ],
           "name": "stdout"
         },
@@ -116,124 +117,69 @@
     {
       "cell_type": "code",
       "metadata": {
-        "id": "hsd_fYYqohhi",
+        "id": "E0NJYOZFoK7r",
         "colab_type": "code",
-        "outputId": "eafefd0d-3b68-4d41-dde1-3a1022692e92",
         "colab": {
           "base_uri": "https://localhost:8080/",
-          "height": 34
-        }
+          "height": 51
+        },
+        "outputId": "e81413e1-a0bf-4e5a-9d66-ee546e41516c"
       },
       "source": [
-        "from google.colab import drive\n",
-        "drive.mount('/content/gdrive')\n",
-        "import matplotlib.pyplot as plt\n",
+        "from skimage import data\n",
+        "from skimage.filters.rank import entropy\n",
+        "from skimage.morphology import disk\n",
         "import numpy as np\n",
-        "import pandas as pd\n",
-        "# importing os module \n",
-        "import os \n",
-        "from sklearn.ensemble import RandomForestClassifier\n",
-        "from sklearn.datasets import make_classification\n",
-        "\n",
-        "#Load in data\n",
-        "os.chdir(\"//content//gdrive//My Drive//PhD casting project//Summary files\")\n",
-        "\n",
-        "#filename='PhaseFraction.csv'\n",
-        "filename='DTAdata.csv'\n",
-        "\n",
-        "data = pd.read_csv(filename)\n",
-        "data.head\n",
-        "data.shape\n",
-        "#F_MC=data['Fraction MC E1']\n",
-        "\n",
-        "## Define Data of Interest\n",
-        "labels=data['Sample ID']\n",
-        "#F_Y_MC=data['Fraction Y E1']\n",
-        "#F_MC=data['Fraction MC E1']\n",
-        "#F_Y_M7=data['Fraction Y E2']\n",
-        "#F_M7=data['Fraction M7C3 E2']"
-      ],
-      "execution_count": 0,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "text": [
-            "Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount(\"/content/gdrive\", force_remount=True).\n"
-          ],
-          "name": "stdout"
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "tbBL8aI11Oll",
-        "colab_type": "code",
-        "outputId": "e8053236-4919-4aae-ddd4-18bb0012976e",
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 392
-        }
-      },
-      "source": [
-        "# %% Visualize Data\n",
-        "plt.figure(figsize=(10,6))\n",
-        "plt.scatter(data['C'],data['Liquidus'])\n",
-        "plt.xlabel('Concentration (wt.%)')\n",
-        "plt.ylabel('Temperature (C)')\n",
-        "plt.show()\n",
-        "\n",
+        "import matplotlib.pyplot as plt\n",
+        "from skimage.util import img_as_ubyte\n",
+        "import skimage\n",
         "\n",
-        "#Random Forest?\n",
+        "#image = skimage.img_as_ubyte(cropim) #8 bit\n",
+        "image=cropim #16 bit\n",
         "\n",
+        "fig, ax = plt.subplots(ncols=2, figsize=(24, 12), sharex=True, sharey=True)\n",
         "\n",
-        "#X, y = make_classification(n_samples=1000, n_features=4,\n",
-        "#                           n_informative=2, n_redundant=0,\n",
-        "#                           random_state=0, shuffle=False)\n",
-        "#clf = RandomForestClassifier(n_estimators=100, max_depth=2,\n",
-        "#                             random_state=0)\n",
-        "#clf.fit(X, y)  \n",
+        "fig.colorbar(ax[0].imshow(image, cmap=plt.cm.gray), ax=ax[0])\n",
+        "ax[0].set_title('Image')\n",
         "\n",
+        "fig.colorbar(ax[1].imshow(entropy(image, disk(5)), cmap=plt.cm.gray), ax=ax[1])\n",
+        "ax[1].set_title('Entropy')\n",
         "\n",
-        "#print(clf.feature_importances_)\n",
+        "for a in ax:\n",
+        "    a.axis('off')\n",
         "\n",
-        "#print(clf.predict([[0, 0, 0, 0]]))"
+        "plt.tight_layout()"
       ],
       "execution_count": 0,
       "outputs": [
         {
-          "output_type": "display_data",
-          "data": {
-            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAm4AAAF3CAYAAAAcmcfdAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzt3X2UZXV95/v3x6bVEtFW6VG7ZQQd\nbC+K0lqSRNRA9NJoZqSDZhSd8SGTEBwZk/GuVrgYGGURyO2JM0nUa1AJNxPEOBFbRMfGBBHjXB+K\ndEs3SkfEByicSyu2xKTUpvneP84uOF3Uw6miTp3ap96vtXpxzm8/nO9xW12f/u3f/v1SVUiSJGn5\ne8igC5AkSVJvDG6SJEktYXCTJElqCYObJElSSxjcJEmSWsLgJkmS1BJ9C25JLk1yZ5LdXW0XJLkx\nyc4k1yRZ17Q/Osknk3wtyU1J3th1zIFm/51JrupXvZIkSctd+jWPW5IXAT8B/ryqntm0Paqq7m5e\nvwU4pqrOTPJ/Ao+uqrcnWQvsAZ5QVT9P8pOqemRfipQkSWqRvvW4VdX1wF1T2u7uensoMJkaCzgs\nSYBHNsfd06/aJEmS2uiQpf7AJBcCrwN+DJzUNL8HuAq4AzgMeFVV3dtse3iSMTpB7uKq2rbEJUuS\nJC0LfbtVCpDkSODqyVulU7adAzy8qs5P8krgBOCtwFOBzwLPrqq7k6yvqvEkTwGuBV5cVd+a4fPO\nAM4AOPTQQ5/79Kc/vR9fS5IkaVHdcMMNP6iqtXPtt+Q9bl0uBz4NnA+8kU5vWgG3JPk28HTgK1U1\nDlBVtya5DtgITBvcquoS4BKA0dHRGhsb6/uXkCRJerCSfLeX/ZZ0OpAkR3e9PRW4uXn9PeDFzT6P\nBzYAtyZ5TJKHNe2H0+mV+/rSVSxJkrR89K3HLckVwInA4Ulup9Oz9rIkG4B7ge8CZza7XwBclmQX\nEODtVfWDJM8H/jTJvXRC5sVVZXCTJEkrUt+CW1WdPk3zh2bY9w7g5Gna/ydw7CKXJkmS1EqunCBJ\nktQSBjdJkqSWMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUksMcsmrFWHbjnG2bt/DHfsm\nWLdmhC2bNrB54/pBlyVJklrI4NZH23aMc86Vu5jYfwCA8X0TnHPlLgDDmyRJmjdvlfbR1u177gtt\nkyb2H2Dr9j0DqkiSJLWZPW59dMe+iXm1S5IeyCEn0v3sceujdWtG5tUuSTrY5JCT8X0TFPcPOdm2\nY3zQpUkDYXDroy2bNjCyetVBbSOrV7Fl04YBVSRJ7eKQE+lg3irto8mufLv4JWlhHHIiHczg1meb\nN643qElDwHFWg7FuzQjj04Q0h5xopfJWqSTNwXFWg+OQE+lgBjdJmoPjrAZn88b1XHTasaxfM0KA\n9WtGuOi0Y+3t1IrlrVJJmoPjrAbLISfS/exxk6Q5OLWPpOXC4CZJc3CclaTlwlulkjQHp/aRtFwY\n3CSpB46zkrQceKtUkiSpJQxukiRJLWFwkyRJagmDmyRJUksY3CRJklrC4CZJktQSBjdJkqSWMLhJ\nkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUkv0NbgluTTJnUl2d7VdkOTGJDuTXJNkXdP+6CSf\nTPK1JDcleWPXMa9P8s3mz+v7WbMkSdJy1e8et8uAU6a0ba2qZ1XVccDVwHlN+5uBr1fVs4ETgT9M\n8tAkjwXOB34BOB44P8lj+ly3JEnSstPX4FZV1wN3TWm7u+vtoUBNbgIOSxLgkc1x9wCbgM9W1V1V\n9SPgszwwDEqSJA29QwbxoUkuBF4H/Bg4qWl+D3AVcAdwGPCqqro3yXrgtq7DbwfWL2G5kiRJy8JA\nHk6oqnOr6gjgcuCspnkTsBNYBxwHvCfJo+Zz3iRnJBlLMrZ3795FrVmSJGnQBv1U6eXAK5rXbwSu\nrI5bgG8DTwfGgSO6jnlS0/YAVXVJVY1W1ejatWv7WLYkSdLSW/LgluTorrenAjc3r78HvLjZ5/HA\nBuBWYDtwcpLHNA8lnNy0SZIkrSh9HeOW5Ao6T4genuR2Ok+HvizJBuBe4LvAmc3uFwCXJdkFBHh7\nVf2gOc8FwFeb/d5VVQc98CBJkrQSpKrm3quFRkdHa2xsbNBlSJIkzSnJDVU1Otd+gx7jJkmSpB4Z\n3CRJklrC4CZJktQSBjdJkqSWMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUksY3CRJklrC\n4CZJktQSBjdJkqSWMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUksY3CRJklrC4CZJktQS\nBjdJkqSWMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUksY3CRJklrC4CZJktQSBjdJkqSW\nMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJaolDBl2Alta2HeNs3b6HO/ZNsG7NCFs2bWDzxvWDLkuS\nJPXA4LaCbNsxzjlX7mJi/wEAxvdNcM6VuwAMb5IktUDfbpUmuTTJnUl2d7VdkOTGJDuTXJNkXdO+\npWnbmWR3kgNJHtts+06SXc22sX7VuxJs3b7nvtA2aWL/AbZu3zOgiiRJ0nz0c4zbZcApU9q2VtWz\nquo44GrgPICq2lpVxzXt5wCfr6q7uo47qdk+2sd6h94d+ybm1S5JkpaXvgW3qroeuGtK291dbw8F\nappDTweu6FddK9m6NSPzapckScvLkj9VmuTCJLcBr6Xpceva9gg6vXQf62ou4JokNyQ5Y+kqHT5b\nNm1gZPWqg9pGVq9iy6YNA6pIWnzbdoxzwsXXctTZn+KEi69l247xQZckSYtmyYNbVZ1bVUcAlwNn\nTdn8r4AvTrlN+oKqeg7wUuDNSV4007mTnJFkLMnY3r17F732ttu8cT0XnXYs69eMEGD9mhEuOu1Y\nH0zQ0Jh8AGd83wTF/Q/gGN4kDYtUTXe3cpFOnhwJXF1Vz5xm2z8HPt29LcnHgf9eVR+e4Xz/CfhJ\nVf3nuT57dHS0xsZ8lkFaSU64+FrGpxmzuX7NCF88+1cGUJEk9SbJDb2M5V/SHrckR3e9PRW4uWvb\no4FfBj7R1XZoksMmXwMnA7uRpGn4AI6kYde3edySXAGcCBye5HbgfOBlSTYA9wLfBc7sOuTXgGuq\n6h+72h4PfDzJZK0frqrP9KtmSe22bs3ItD1uPoAjaVj0LbhV1enTNH9olv0vozOFSHfbrcCzF7Uw\nSUNry6YNB00yDT6AI2m4uHKCpKEx+aCNy7pJGlYGN0lDZfPG9QY1SUNryacDkSRJ0sIY3CRJklrC\n4CZJktQSBjdJkqSWMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUksY3CRJklrC4CZJktQS\nBjdJkqSWMLhJkiS1hMFNkiSpJQxukiRJLWFwkyRJagmDmyRJUkscMugCJElajrbtGGfr9j3csW+C\ndWtG2LJpA5s3rh90WVrhDG6SJE2xbcc451y5i4n9BwAY3zfBOVfuAjC8aaC8VSpJ0hRbt++5L7RN\nmth/gK3b9wyoIqnD4CZJ0hR37JuYV7u0VAxukiRNsW7NyLzapaVicJMkaYotmzYwsnrVQW0jq1ex\nZdOGAVUkdfhwgiRJU0w+gOBTpVpuDG6SJE1j88b1BjUtO94qlSRJagmDmyRJUkt4q1SSBsSZ+SXN\nl8FNkgbAmfklLYS3SiVpAJyZX9JCzNrjluSJwKuAFwLrgAlgN/Ap4Jqqqr5XKEnz0Jbbj87ML2kh\nZuxxS/JB4C+aff4IeCPwVuBvgc3AF5O8YCmKlKReTN5+HN83QXH/7cdtO8YHXdoDODO/pIWY7Vbp\nn1TVi6vq3VV1fVXdXFU7q+qjVfUm4FeAO2c6OMmlSe5Msrur7YIkNybZmeSaJOua9i1N284ku5Mc\nSPLYZtspSfYkuSXJ2Yv0vSUNoTbdfnRmfkkLMVtwG0/ygL9BkmxI8riq+mlV/f0sx18GnDKlbWtV\nPauqjgOuBs4DqKqtVXVc034O8PmquivJKuC9wEuBY4DTkxzT87eTtKK06fbj5o3ruei0Y1m/ZoQA\n69eMcNFpxy7L27qSlo/Zxrj9MfABYOo/VZ8I/B7wb2Y7cVVdn+TIKW13d709FJhujNzpwBXN6+OB\nW6rqVoAkHwFOBb4+22dLWpnWrRlhfJqQtlxvPzozv6T5mq3H7WlV9bmpjVV1HXDcQj8wyYVJbgNe\nS9Pj1rXtEXR66T7WNK0Hbuva5famTZIewNuPkobdbMHtsFm2rV7oB1bVuVV1BHA5cNaUzf8K+GJV\n3bWQcyc5I8lYkrG9e/cutERJLdW224/bdoxzwsXXctTZn+KEi69dlg9RSFpeZrtV+q0km6pqe3dj\nkpOBby/CZ18OfBo4v6vt1dx/mxRgHDii6/2TmrZpVdUlwCUAo6OjTlUirUBtuf3oBLySFmK24PZW\n4Ook1wE3NG2jwC8D/3IhH5bk6Kr6ZvP2VODmrm2Pbs7dPXbuq8DRSY6iE9heDbxmIZ8tScvJbE/A\nGtwkzWTG4FZVNyc5lk6QembT/GXgrKqa8xGtJFcAJwKHJ7mdTs/ay5onVe8Fvguc2XXIr9GZ1Pcf\nu2q4J8lZwHZgFXBpVd00j+8nSctSm56AlbR8zLpyQhPQPrCQE1fV6dM0f2iW/S+jM4XI1PZP07ml\nKklDo21PwEpaHmZbOeFzSd40OUluV/shSV6U5ENJ3tj/EiVp+PgErKSFmK3H7VeB3wQ+nmQ9cBcw\nAjwc+GvgvVU11v8SJWn4TI5ja8O6qpKWj/SyTnyShwH/DJioqh/0vapFMDo6WmNj5kpJkrT8Jbmh\nqkbn2m/WMW6TqupnHDwRriRJkpbYbBPwSpIkaRkxuEmSJLVET7dKkzwJOLqqPteMdzuke741SZK0\nfG3bMe6DMENizuCW5DforCn6aOCpwJOB9wEv6W9pkrSy+MtV/eDyasOll1ulbwF+EbgboKr+ns4T\nppKkRTL5y3V83wTF/b9cXXheD9Zsy6upfXoJbj+tqp9PvkmyCkj/SpKklcdfruoXl1cbLr0Ety8m\neRvw8CQnAX8JXN3fsiRpZfGXq/plpmXUXF6tnXoJbm8D/gG4Gfgd4G+Ac/tZlCRN2rZjnBMuvpaj\nzv4UJ1x87dDeOvSXq/rF5dWGy6wPJzS3Rf+sql4H/N9LU5IkdaykQdVbNm046LuCv1y1OFxebbjM\nGtyq6kCSpyRZXVX7l6ooSYLZx33N9EunrU9m+stV/bR543r/vzQkepnH7VvAF5J8Arhv7raq+uO+\nVSVJzH/cV9t76PzlKmkuvYxx+x7wWeARwNquP5LUV/Md9+WTmZKG3Zw9blX1e0tRiCRNNd9xXz6Z\nKWnY9bJywmeBmtpeVSf3pSJJasx33Ne6NSOMTxPSfDJT0rDoZYzbO7pePxx4BfCz/pQjSQebz7gv\nn8yUNOx6uVX65SlNn08ytU2SBs4nMyUNu15ulT6q6+1DgOcCj+lbRZL0IPhkpqRh1sut0pvojHEL\ncA/wbeC3+lmUJEmSHqiX4PaUqZPvJunlOEmSJC2iXuZxm24821cWuxBJkiTNbsaesyT/DHgiMJLk\nWDq3SgEeRWcyXkmSJC2h2W55/irwG8CTgPd1tf8D4KS8kpaltq5VKkm9mDG4VdWfAX+W5F9X1UeX\nsCb1wF9O0gO1fa1SSZpLL/O4fTTJJuAZdCbgnWz//X4Wppn5y0ma3mxrlfqzIWkYzPlwQpL3Aa8H\n3gqMAP8G+Bd9rkuzcCFtaXquVSpp2PXyVOkLquo1wA+bBed/AYPbQPnLSZreTGuSulappGHRS3D7\n6eR/kzyheb+ufyVpLv5ykqa3ZdMGRlavOqjNtUolDZNegtunk6wB/jOwE/gO4MMKA+QvJ2l6mzeu\n56LTjmX9mhECrF8zwkWnHev4NklDI1U188bkIcDzJheaTzICjFTVXUtU34KNjo7W2NjYoMvoG58q\nlSRpeCS5oapG59pv1qdKq+reJH8KHNe8nwAcSLUMuJC2Vhr/sSJJvd0q/VySU+d74iSXJrkzye6u\ntguS3JhkZ5Jrkqzr2nZi035Tks93tX8nya5m2/B2oUma0eQUOOP7JijunwJn247xQZcmSUuql+D2\nBuDjSSaS3JXkR0l6uVV6GXDKlLatVfWsqjoOuBo4D6AZQ/c+4OVV9Qzg16ccd1JVHddLF6Kk4eMU\nOJLUMecEvMDhCzlxVV2f5MgpbXd3vT0UmBxg9xrgyqr6XrPfnQv5TEnDySlwJKljzh63qjpApwfs\n7c3rJ9KMeVuIJBcmuQ14LU2PG/A04DFJrktyQ5LXdZcAXNO0n7HQz5XUXk6BI0kdvayc8B7gJODf\nNk3/BLx/oR9YVedW1RHA5cBZTfMhwHPpLGy/Cfi9JE9rtr2gqp4DvBR4c5IXzVLrGUnGkozt3bt3\noSVKWmacAkeSOnoZ4/b8qvptmol4m6lAHroIn3058Irm9e3A9qr6x6r6AXA98Ozm88ab/94JfBw4\nfqYTVtUlVTVaVaNr165dhBIlLQfOzyZJHb2McdvfzOdWAEkeB9y7kA9LcnRVfbN5eypwc/P6E8B7\nkhxCJxT+AvBfkhwKPKSq/qF5fTLwroV8tqR2cwocSeotuL0X+BiwNsk7gX8NvHOug5JcAZwIHJ7k\nduB84GVJNtAJft8FzgSoqm8k+QxwY7Ptg1W1O8lT6DzROlnrh6vqM/P7ipIkScNh1pUT7tspeQbw\nkubt31TV7tn2Xw6GfeUESZI0PBZl5YQuq4D9dG6X9jIuTlILuTqBJC1vcwa3JOfSmWft40CADye5\nvKou6ndxkpbO5OoEkxPdTq5OALQqvBk+JQ2zXnrPXkdnofl3VNW5dJ7qfENfq5K05IZhdQKXxpI0\n7HoJbt/n4J65Q5o2SUNkGFYnGIbwKUmz6WWM213ATUm20xnjdjLw1STvBqiqt/axPklLZN2aEcan\nCWltWp1gGMKnJM2ml+D2qebPpC/1qRZJA7Rl04aDxrhB+1YnGIbwKUmzmTO4VdWHlqIQSYM1OYC/\nzQP7hyF8StJsenmq9BTgAuDJzf4Bqqoe2+faJC2xtq9OMAzhU5Jm08ut0vfQWS1hFwtc6kqSlkrb\nw6ckzaaX4HY7sLOqDG2SJEkD1EtwexvwySTXAT+bbKyqP+5XUZIkSXqgXoLbO+ksd7UGb5VKreDq\nAZI0nHoJbkdU1TP7XomkRTEsS1dJkh6ol5UTtif5lb5XImlRuHpAe2zbMc4JF1/LUWd/ihMuvtal\nuSTNqZcet98A/mOSfwJ+jtOBSMuaqwe0gz2jkhailx63w4HVwKOBtc37tf0sStLCzbRKgKsHLC/2\njEpaiDmDW1UdAH4deHvz+onAcf0uTNLCbNm0gZHVqw5qc/WA5ceeUUkLMWdwS/Ie4CTg3zZN/wS8\nv59FSVq4zRvXc9Fpx7J+zQgB1q8Z4aLTjvX22zJjz6ikhehljNvzq+o5SXYAVNVdSR7a57okPQiu\nHrD8ua6qpIXoJbjtT/IQoACSPA7nc5OkB8V1VSUtxIzBLckhVXUP8F7gY8DaJO+ks27pO5eoPkka\nGtNNjPzFs51tSVLvZutx+wrwnKr68yQ3AC+hMxXIr1fV7iWpTpKGhNN/SFoMswW3TL6oqpuAm/pf\njiQNp9mm/zC4aTouXafpzBbc1iZ560wbq+rdfahHkoaS039oPuyh1Uxmmw5kFfBI4LAZ/kiSeuT0\nH5oPJ2jWTGbrcft+Vb1rySqRpCHm9B+aD3toNZPZetwyyzZJ0jw4MbLmwx5azWS2HrcXL1kVkrQC\nODGyemUPrWYyY3CrqruWshBJktThBM2aSS8rJ0iSpCVmD62mM+ci85IkSVoeDG6SJEktYXCTJElq\nCYObJElSS/QtuCW5NMmdSXZ3tV2Q5MYkO5Nck2Rd17YTm/abkny+q/2UJHuS3JLk7H7VK0mStNz1\ns8ftMuCUKW1bq+pZVXUccDVwHkCSNcD7gJdX1TOAX2/aVwHvBV4KHAOcnuSYPtYsSZK0bPVtOpCq\nuj7JkVPa7u56eyhQzevXAFdW1fea/e5s2o8HbqmqWwGSfAQ4Ffh6v+qWpOls2zHunFqSBm7J53FL\nciHwOuDHwElN89OA1Umuo7OA/R9V1Z8D64Hbug6/HfiFpatWkjqhrXsW+/F9E5xz5S4Aw5ukJbXk\nDydU1blVdQRwOXBW03wI8FzgV4FNwO8ledp8z53kjCRjScb27t27aDVLWtm2bt9z0NJDABP7D7B1\n+54BVSRppRrkU6WXA69oXt8ObK+qf6yqHwDXA88GxoEjuo55UtM2raq6pKpGq2p07dq1fSpb0kpz\nx76JebVLUr8saXBLcnTX21OBm5vXnwBekOSQJI+gczv0G8BXgaOTHJXkocCrgauWsmZJWrdmZF7t\nktQv/ZwO5Arg/wU2JLk9yb8DLk6yO8mNwMnA7wBU1TeAzwA3Al8BPlhVu6vqHjq3U7fTCXIfraqb\n+lWzJE1ny6YNjKxedVDbyOpVbNm0YUAVSVqpUlVz79VCo6OjNTY2NugyJA0JnyqV1E9Jbqiq0bn2\nW/KnSiWpjTZvXG9QkzRwLnklSZLUEgY3SZKkljC4SZIktYTBTZIkqSUMbpIkSS1hcJMkSWoJg5sk\nSVJLGNwkSZJawuAmSZLUEq6cIEk9cMkrScuBwU2S5rBtxzjnXLmLif0HABjfN8E5V+4CMLxJWlLe\nKpWkOWzdvue+0DZpYv8Btm7fM6CKJK1UBjdJmsMd+ybm1S5J/WJwk6Q5rFszMq92SeoXg5skzWHL\npg2MrF51UNvI6lVs2bRhQBVJWql8OEGS5jD5AIJPlUoaNIObpKHSr2k7Nm9cb1CTNHAGN0lDw2k7\nJA07x7hJGhpO2yFp2NnjJmloOG2HpNkMwwoo9rhJGhpO2yFpJpNDKcb3TVDcP5Ri247xQZc2LwY3\nSUPDaTskzWRYhlJ4q1TS0HDaDkkzGZahFAY3SUPFaTskTWfdmhHGpwlpbRtK4a1SSZI09IZlKIU9\nbpIkaegNy1AKg5skSVoRhmEohbdKJUmSWsLgJkmS1BIGN0mSpJYwuEmSJLWEwU2SJKklDG6SJEkt\n0bfgluTSJHcm2d3VdkGSG5PsTHJNknVN+4lJfty070xyXtcx30myq2kf61e9kiRJy10/e9wuA06Z\n0ra1qp5VVccBVwPndW37QlUd1/x515TjTmraR/tYryRJ0rLWt+BWVdcDd01pu7vr7aFA9evzJUmS\nhs2Sj3FLcmGS24DXcnCP2y8l+VqS/5HkGV3tBVyT5IYkZyxpsZIkScvIkge3qjq3qo4ALgfOapr/\nDnhyVT0b+BNgW9chL6iq5wAvBd6c5EUznTvJGUnGkozt3bu3T99AkiRpMAb5VOnlwCugcwu1qn7S\nvP40sDrJ4c378ea/dwIfB46f6YRVdUlVjVbV6Nq1a/tdvyRJ0pJa0uCW5Oiut6cCNzftT0iS5vXx\nTV0/THJoksOa9kOBk4HdSJIkrUCH9OvESa4ATgQOT3I7cD7wsiQbgHuB7wJnNru/EnhTknuACeDV\nVVVJHg98vMl0hwAfrqrP9KtmSZKk5SxVw/lg5+joaI2NOe2bJEla/pLc0Mu0Z66cIEmS1BIGN0mS\npJYwuEmSJLWEwU2SJKklDG6SJEktYXCTJElqCYObJElSSxjcJEmSWsLgJkmS1BIGN0mSpJYwuEmS\nJLWEwU2SJKklDG6SJEktYXCTJElqCYObJElSSxwy6AIkrVzbdoyzdfse7tg3wbo1I2zZtIHNG9cP\nuixJWrYMbpIGYtuOcc65chcT+w8AML5vgnOu3AVgeJOkGRjcJPVksXvHtm7fc19omzSx/wBbt+8x\nuEnSDAxukubUj96xO/ZNzKtdkuTDCZJ6MFvv2EKtWzMyr3ZJksFNUg/60Tu2ZdMGRlavOqhtZPUq\ntmzasOBzStKwM7hJmlM/esc2b1zPRacdy/o1IwRYv2aEi0471vFtkjQLx7hJmtNJT1/LX3zpe9O2\nPxibN643qEnSPNjjJmlOn7t577zaJUn9YXCTNCefAJWk5cHgJmlOPgEqScuDwU3SnHwCVJKWBx9O\nkDSnyQcIXFdUkgbL4CapJz4BKkmD561SSZKkljC4SZIktYTBTZIkqSUMbpIkSS1hcJMkSWqJvgW3\nJJcmuTPJ7q62C5LcmGRnkmuSrGvaT0zy46Z9Z5Lzuo45JcmeJLckObtf9UqSJC13/exxuww4ZUrb\n1qp6VlUdB1wNnNe17QtVdVzz510ASVYB7wVeChwDnJ7kmD7WLEmStGz1LbhV1fXAXVPa7u56eyhQ\nc5zmeOCWqrq1qn4OfAQ4dVELlSRJaoklH+OW5MIktwGv5eAet19K8rUk/yPJM5q29cBtXfvc3rRJ\nkiStOEse3Krq3Ko6ArgcOKtp/jvgyVX1bOBPgG0LOXeSM5KMJRnbu3fv4hQsSZK0TAzyqdLLgVdA\n5xZqVf2kef1pYHWSw4Fx4IiuY57UtE2rqi6pqtGqGl27dm3/KpckSRqAJQ1uSY7uensqcHPT/oQk\naV4f39T1Q+CrwNFJjkryUODVwFVLWbMkSdJy0bdF5pNcAZwIHJ7kduB84GVJNgD3At8Fzmx2fyXw\npiT3ABPAq6uqgHuSnAVsB1YBl1bVTf2qWZIkaTlLJx8Nn9HR0RobGxt0GZIkSXNKckNVjc61nysn\nSJIktYTBTZIkqSX6NsZNklaibTvG2bp9D3fsm2DdmhG2bNrA5o1OPylpcRjcJGmRbNsxzjlX7mJi\n/wEAxvdNcM6VuwAMb5IWhbdKJWmRbN2+577QNmli/wG2bt8zoIokDRuDmyQtkjv2TcyrXZLmy+Am\nSYtk3ZqRebVL0nwZ3CRpkWzZtIGR1asOahtZvYotmzYMqCJJw8aHEyRpkUw+gOBTpZL6xeAmSYto\n88b1BjVJfeOtUkmSpJYwuEmSJLWEwU2SJKklDG6SJEktYXCTJElqCYObJElSSxjcJEmSWsLgJkmS\n1BIGN0mSpJYwuEmSJLVEqmrQNfRFkr3Adwddx5A6HPjBoItQT7xW7eB1agevUzu09To9uarWzrXT\n0AY39U+SsaoaHXQdmpvXqh0A0QqdAAAInElEQVS8Tu3gdWqHYb9O3iqVJElqCYObJElSSxjctBCX\nDLoA9cxr1Q5ep3bwOrXDUF8nx7hJkiS1hD1ukiRJLWFw00GSnJJkT5Jbkpw9zfYzk+xKsjPJ3yY5\npmk/MslE074zyfuXvvqVY67r1LXfK5JUktGutnOa4/Yk2bQ0Fa9MC71O/jwtvR7+7ntDkr1d1+Q3\nu7a9Psk3mz+vX9rKV5YHeZ0OdLVftbSVLx5vleo+SVYBfw/878DtwFeB06vq6137PKqq7m5evxz4\n91V1SpIjgaur6plLXvgK08t1avY7DPgU8FDgrKoaa4L2FcDxwDrgr4GnVdWBJfwKK8KDvE5H4s/T\nkunx7743AKNVddaUYx8LjAGjQAE3AM+tqh8tTfUrx4O5Ts22n1TVI5eo3L6xx03djgduqapbq+rn\nwEeAU7t3mAxtjUPp/EWlpTXndWpcAPwB8NOutlOBj1TVz6rq28Atzfm0+B7MddLS6vVaTWcT8Nmq\nuqsJa58FTulTnSvdg7lOQ8Pgpm7rgdu63t/etB0kyZuTfAv4v4C3dG06KsmOJJ9P8sL+lrqizXmd\nkjwHOKKqPjXfY7VoHsx1An+ellKvPxevSHJjkr9KcsQ8j9WD92CuE8DDk4wl+VKSzX2ttI8Mbpq3\nqnpvVT0VeDvwjqb5+8A/r6qNwFuBDyd51KBqXMmSPAR4N/B/DLoWzWyO6+TP0/LzSeDIqnoWnV61\n/2fA9Wh6s12nJzcrKrwG+K9JnjqIAh8sg5u6jQPd/zp5UtM2k48AmwGaW28/bF7fAHwLeFqf6lzp\n5rpOhwHPBK5L8h3gF4GrmoHv873GWrgFXyd/npbcnD8XVfXDqvpZ8/aDwHN7PVaL5sFcJ6pqvPnv\nrcB1wMZ+FtsvBjd1+ypwdJKjkjwUeDVw0JM3SY7uevurwDeb9rXNwFGSPAU4Grh1SapeeWa9TlX1\n46o6vKqOrKojgS8BL6+qsWa/Vyd5WJKj6Fynryz9V1gRFnyd/Hlacr383ffErrcvB77RvN4OnJzk\nMUkeA5zctGnxLfg6NdfnYc3rw4ETgIMeFGqLQwZdgJaPqronyVl0/tJZBVxaVTcleRcwVlVXAWcl\neQmwH/gRMPno+4uAdyXZD9wLnFlVdy39txh+PV6nmY69KclH6fyFdQ/wZp8o7Y8Hc53w52lJ9Xit\n3tI8SX8PcBfwhubYu5JcQCdUALzLa9UfD+Y6Af8b8KdJ7qXTaXXx1Ce828LpQCRJklrCW6WSJEkt\nYXCTJElqCYObJElSSxjcJEmSWsLgJkmS1BIGN0mSpJYwuEnqqyRPSPKRJN9KckOSTycZ6CoASX43\nySMWcNwbkqzrev/BJMcsUk2bk5zX474nJnn+DNtOaNZpHJucMDvJmiTXNMtsTe73182EsZJaxOAm\nqW+SBPg4cF1VPbWqngucAzx+sJXxu8C0wW1yxYIZvAG4L7hV1W8u4iSebwPe1+O+JwLTBjc6a5++\njM53PLNpewfw+1V1b9d+/w349/MvU9IgGdwk9dNJwP6qev9kQ1V9raq+kI6tSXYn2ZXkVXBfb9J1\nSf4qyc1JLm8CIEmel+R/Jvlakq8kOSzJquY8X216mn57tvMkeQud8PW5JJ9r9v1Jkj9M8jXgl5Kc\n15xvd5JLmuNeCYwClyfZmWSkOf9oc47Tm++xO8kfTH7f5twXNjV/KckDQmvTA/mzqvpB832+3Xzm\nmiQHkryo2e/6phftTOA/NnW8cMrp9tMJpY8A9qezkPYRVXXdlP2uAk5fwDWVNEAGN0n99Ezghhm2\nnQYcBzwbeAmwtWudwY10eoyOAZ4CnNCsTfiXwO9U1eQxE8C/A35cVc8Dngf8VjrrsE57nqr6Y+AO\n4KSqOqnZ71Dgy1X17Kr6W+A9VfW8qnomMAL8y6r6K2AMeG1VHVdVE5NfpLl9+gfArzTf6XlJNned\n+0tNzdcDvzXN/xYnAH8H0CxBtqep+QVN+wvTWWfxiKr6JvB+4L80dXxhyrkuAv6cTs/me4AL6fS4\nHaSqfgQ8LMnjpqlH0jJlcJM0KC8ArqiqA1X1/wGfpxO8AL5SVbc3t/Z2AkcCG4DvV9VXAarq7qq6\nh86i3q9LshP4MvA4Oouyz3Se6RwAPtb1/qQkX06yi04Ye8Yc3+V5dG4H721qupzOeqMAPweubl7f\nMEMNTwT2dr3/QnP8i+gEsRc0n/HVBx56sKraWVW/2ITSpwDfp3PX+i+T/MWUHr876br1K2n5M7hJ\n6qebgOcu4Lifdb0+ABwyy74B/kPT+3RcVR1VVdfM8zw/bXq6SPJwOmPNXllVxwIfAB6+gO8waX/d\nvyj0TDVMTPmM64EXAscDnwbW0BnXNrV3bUbN7eV3ABcA59MZQ/cB4C1duz28+WxJLWFwk9RP19K5\nHXfGZEOSZzXjsr4AvKoZ07WWTu/SV2Y51x7giUme15znsCSHANuBNyVZ3bQ/Lcmhc9T1D8BhM2yb\nDFA/SPJI4JU9HPcV4JeTHN483HA6nR7EXn0D+BdTzvd84N6q+imd3sLfphPo5qp/0uuAT1fVXXTG\nu93b/HkE3BfsngB8Zx51Shqw2f4VK0kPSlVVkl8D/muStwM/pRMUfhf4W+CXgK8BBbytqv5XkqfP\ncK6fNw8w/EmSETo9RS8BPkjn9uPfNWFkL7B5unN0uQT4TJI7usa5TX7OviQfAHYD/4uDb09eBrw/\nyURT++Qx309yNvA5Oj2An6qqT8xRQ7frgT9Mkur4WZLbgC81279AJwzuat5/EvirJKcC/wF4DDBa\nVecBpDPVyRvo3EYGeDednrufA69p2p5LZ+zdPfOoU9KA5f4efEnSoCT5I+CTVfXXS/h5V1XV3yzF\n50laHN4qlaTl4feZYW65PtltaJPaxx43SZKklrDHTZIkqSUMbpIkSS1hcJMkSWoJg5skSVJLGNwk\nSZJa4v8Hv8y1PHe9SDgAAAAASUVORK5CYII=\n",
-            "text/plain": [
-              "<Figure size 720x432 with 1 Axes>"
-            ]
-          },
-          "metadata": {
-            "tags": []
-          }
+          "output_type": "stream",
+          "text": [
+            "/usr/local/lib/python3.6/dist-packages/skimage/filters/rank/generic.py:104: UserWarning: Bad rank filter performance is expected due to a large number of bins (65536), equivalent to an approximate bitdepth of 16.0.\n",
+            "  \"bitdepth of {:.1f}.\".format(n_bins, np.log2(n_bins)))\n"
+          ],
+          "name": "stderr"
         }
       ]
     },
     {
       "cell_type": "code",
       "metadata": {
-        "id": "7slpzDth25jB",
+        "id": "ZXbfLdIhrGTG",
         "colab_type": "code",
         "colab": {}
       },
       "source": [
-        "from sklearn.ensemble import RandomForestClassifier\n",
-        "from sklearn.datasets import make_classification\n",
-        "from sklearn.tree import DecisionTreeClassifier\n",
-        "\n",
-        "# Make a decision tree and train\n",
-        "tree = DecisionTreeClassifier(random_state=RSEED)\n",
-        "tree.fit(X, y)\n",
+        "#Edge Detection\n",
+        "im = np.zeros((256, 256))\n",
+        "im[64:-64, 64:-64] = 1\n",
         "\n",
-        "print(f'Model Accuracy: {tree.score(X, y)}')\n",
+        "im = ndimage.rotate(im, 15, mode='constant')\n",
+        "im = ndimage.gaussian_filter(im, 8)\n",
         "\n",
-        "Model Accuracy: 1.0"
+        "sx = ndimage.sobel(im, axis=0, mode='constant')\n",
+        "sy = ndimage.sobel(im, axis=1, mode='constant')\n",
+        "sob = np.hypot(sx, sy)"
       ],
       "execution_count": 0,
       "outputs": []